3 from __future__ import unicode_literals
14 from .common import InfoExtractor, SearchInfoExtractor
15 from ..jsinterp import JSInterpreter
16 from ..swfinterp import SWFInterpreter
17 from ..compat import (
20 compat_urllib_parse_unquote,
21 compat_urllib_parse_unquote_plus,
22 compat_urllib_parse_urlencode,
23 compat_urllib_parse_urlparse,
32 get_element_by_attribute,
52 class YoutubeBaseInfoExtractor(InfoExtractor):
53 """Provide base functions for Youtube extractors"""
54 _LOGIN_URL = 'https://accounts.google.com/ServiceLogin'
55 _TWOFACTOR_URL = 'https://accounts.google.com/signin/challenge'
56 _PASSWORD_CHALLENGE_URL = 'https://accounts.google.com/signin/challenge/sl/password'
57 _NETRC_MACHINE = 'youtube'
58 # If True it will raise an error if no login info is provided
59 _LOGIN_REQUIRED = False
61 def _set_language(self):
63 '.youtube.com', 'PREF', 'f1=50000000&hl=en',
64 # YouTube sets the expire time to about two months
65 expire_time=time.time() + 2 * 30 * 24 * 3600)
67 def _ids_to_results(self, ids):
69 self.url_result(vid_id, 'Youtube', video_id=vid_id)
74 Attempt to log in to YouTube.
75 True is returned if successful or skipped.
76 False is returned if login failed.
78 If _LOGIN_REQUIRED is set and no authentication was provided, an error is raised.
80 (username, password) = self._get_login_info()
81 # No authentication to be performed
83 if self._LOGIN_REQUIRED:
84 raise ExtractorError('No login info available, needed for using %s.' % self.IE_NAME, expected=True)
87 login_page = self._download_webpage(
88 self._LOGIN_URL, None,
89 note='Downloading login page',
90 errnote='unable to fetch login page', fatal=False)
91 if login_page is False:
94 login_form = self._hidden_inputs(login_page)
97 'checkConnection': 'youtube',
102 login_results = self._download_webpage(
103 self._PASSWORD_CHALLENGE_URL, None,
104 note='Logging in', errnote='unable to log in', fatal=False,
105 data=urlencode_postdata(login_form))
106 if login_results is False:
109 error_msg = self._html_search_regex(
110 r'<[^>]+id="errormsg_0_Passwd"[^>]*>([^<]+)<',
111 login_results, 'error message', default=None)
113 raise ExtractorError('Unable to login: %s' % error_msg, expected=True)
115 if re.search(r'id="errormsg_0_Passwd"', login_results) is not None:
116 raise ExtractorError('Please use your account password and a two-factor code instead of an application-specific password.', expected=True)
119 # TODO add SMS and phone call support - these require making a request and then prompting the user
121 if re.search(r'(?i)<form[^>]+id="challenge"', login_results) is not None:
122 tfa_code = self._get_tfa_info('2-step verification code')
125 self._downloader.report_warning(
126 'Two-factor authentication required. Provide it either interactively or with --twofactor <code>'
127 '(Note that only TOTP (Google Authenticator App) codes work at this time.)')
130 tfa_code = remove_start(tfa_code, 'G-')
132 tfa_form_strs = self._form_hidden_inputs('challenge', login_results)
134 tfa_form_strs.update({
139 tfa_data = urlencode_postdata(tfa_form_strs)
141 tfa_req = sanitized_Request(self._TWOFACTOR_URL, tfa_data)
142 tfa_results = self._download_webpage(
144 note='Submitting TFA code', errnote='unable to submit tfa', fatal=False)
146 if tfa_results is False:
149 if re.search(r'(?i)<form[^>]+id="challenge"', tfa_results) is not None:
150 self._downloader.report_warning('Two-factor code expired or invalid. Please try again, or use a one-use backup code instead.')
152 if re.search(r'(?i)<form[^>]+id="gaia_loginform"', tfa_results) is not None:
153 self._downloader.report_warning('unable to log in - did the page structure change?')
155 if re.search(r'smsauth-interstitial-reviewsettings', tfa_results) is not None:
156 self._downloader.report_warning('Your Google account has a security notice. Please log in on your web browser, resolve the notice, and try again.')
159 if re.search(r'(?i)<form[^>]+id="gaia_loginform"', login_results) is not None:
160 self._downloader.report_warning('unable to log in: bad username or password')
164 def _real_initialize(self):
165 if self._downloader is None:
168 if not self._login():
172 class YoutubeEntryListBaseInfoExtractor(YoutubeBaseInfoExtractor):
173 # Extract entries from page with "Load more" button
174 def _entries(self, page, playlist_id):
175 more_widget_html = content_html = page
176 for page_num in itertools.count(1):
177 for entry in self._process_page(content_html):
180 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
184 more = self._download_json(
185 'https://youtube.com/%s' % mobj.group('more'), playlist_id,
186 'Downloading page #%s' % page_num,
187 transform_source=uppercase_escape)
188 content_html = more['content_html']
189 if not content_html.strip():
190 # Some webpages show a "Load more" button but they don't
193 more_widget_html = more['load_more_widget_html']
196 class YoutubePlaylistBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
197 def _process_page(self, content):
198 for video_id, video_title in self.extract_videos_from_page(content):
199 yield self.url_result(video_id, 'Youtube', video_id, video_title)
201 def extract_videos_from_page(self, page):
204 for mobj in re.finditer(self._VIDEO_RE, page):
205 # The link with index 0 is not the first video of the playlist (not sure if still actual)
206 if 'index' in mobj.groupdict() and mobj.group('id') == '0':
208 video_id = mobj.group('id')
209 video_title = unescapeHTML(mobj.group('title'))
211 video_title = video_title.strip()
213 idx = ids_in_page.index(video_id)
214 if video_title and not titles_in_page[idx]:
215 titles_in_page[idx] = video_title
217 ids_in_page.append(video_id)
218 titles_in_page.append(video_title)
219 return zip(ids_in_page, titles_in_page)
222 class YoutubePlaylistsBaseInfoExtractor(YoutubeEntryListBaseInfoExtractor):
223 def _process_page(self, content):
224 for playlist_id in orderedSet(re.findall(
225 r'<h3[^>]+class="[^"]*yt-lockup-title[^"]*"[^>]*><a[^>]+href="/?playlist\?list=([0-9A-Za-z-_]{10,})"',
227 yield self.url_result(
228 'https://www.youtube.com/playlist?list=%s' % playlist_id, 'YoutubePlaylist')
230 def _real_extract(self, url):
231 playlist_id = self._match_id(url)
232 webpage = self._download_webpage(url, playlist_id)
233 title = self._og_search_title(webpage, fatal=False)
234 return self.playlist_result(self._entries(webpage, playlist_id), playlist_id, title)
237 class YoutubeIE(YoutubeBaseInfoExtractor):
238 IE_DESC = 'YouTube.com'
239 _VALID_URL = r"""(?x)^
241 (?:https?://|//) # http(s):// or protocol-independent URL
242 (?:(?:(?:(?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/|
243 (?:www\.)?deturl\.com/www\.youtube\.com/|
244 (?:www\.)?pwnyoutube\.com/|
245 (?:www\.)?yourepeat\.com/|
246 tube\.majestyc\.net/|
247 youtube\.googleapis\.com/) # the various hostnames, with wildcard subdomains
248 (?:.*?\#/)? # handle anchor (#/) redirect urls
249 (?: # the various things that can precede the ID:
250 (?:(?:v|embed|e)/(?!videoseries)) # v/ or embed/ or e/
251 |(?: # or the v= param in all its forms
252 (?:(?:watch|movie)(?:_popup)?(?:\.php)?/?)? # preceding watch(_popup|.php) or nothing (like /?v=xxxx)
253 (?:\?|\#!?) # the params delimiter ? or # or #!
254 (?:.*?[&;])?? # any other preceding param (like /?s=tuff&v=xxxx or ?s=tuff&v=V36LpHqtcDY)
259 youtu\.be| # just youtu.be/xxxx
260 vid\.plus| # or vid.plus/xxxx
261 zwearz\.com/watch| # or zwearz.com/watch/xxxx
263 |(?:www\.)?cleanvideosearch\.com/media/action/yt/watch\?videoId=
265 )? # all until now is optional -> you can pass the naked ID
266 ([0-9A-Za-z_-]{11}) # here is it! the YouTube video ID
267 (?!.*?\blist=) # combined list/video URLs are handled by the playlist IE
268 (?(1).+)? # if we found the ID, everything can follow
270 _NEXT_URL_RE = r'[\?&]next_url=([^&]+)'
272 '5': {'ext': 'flv', 'width': 400, 'height': 240, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
273 '6': {'ext': 'flv', 'width': 450, 'height': 270, 'acodec': 'mp3', 'abr': 64, 'vcodec': 'h263'},
274 '13': {'ext': '3gp', 'acodec': 'aac', 'vcodec': 'mp4v'},
275 '17': {'ext': '3gp', 'width': 176, 'height': 144, 'acodec': 'aac', 'abr': 24, 'vcodec': 'mp4v'},
276 '18': {'ext': 'mp4', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 96, 'vcodec': 'h264'},
277 '22': {'ext': 'mp4', 'width': 1280, 'height': 720, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
278 '34': {'ext': 'flv', 'width': 640, 'height': 360, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
279 '35': {'ext': 'flv', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
280 # itag 36 videos are either 320x180 (BaW_jenozKc) or 320x240 (__2ABJjxzNo), abr varies as well
281 '36': {'ext': '3gp', 'width': 320, 'acodec': 'aac', 'vcodec': 'mp4v'},
282 '37': {'ext': 'mp4', 'width': 1920, 'height': 1080, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
283 '38': {'ext': 'mp4', 'width': 4096, 'height': 3072, 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264'},
284 '43': {'ext': 'webm', 'width': 640, 'height': 360, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
285 '44': {'ext': 'webm', 'width': 854, 'height': 480, 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8'},
286 '45': {'ext': 'webm', 'width': 1280, 'height': 720, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
287 '46': {'ext': 'webm', 'width': 1920, 'height': 1080, 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8'},
288 '59': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
289 '78': {'ext': 'mp4', 'width': 854, 'height': 480, 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264'},
293 '82': {'ext': 'mp4', 'height': 360, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
294 '83': {'ext': 'mp4', 'height': 480, 'format_note': '3D', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -20},
295 '84': {'ext': 'mp4', 'height': 720, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
296 '85': {'ext': 'mp4', 'height': 1080, 'format_note': '3D', 'acodec': 'aac', 'abr': 192, 'vcodec': 'h264', 'preference': -20},
297 '100': {'ext': 'webm', 'height': 360, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 128, 'vcodec': 'vp8', 'preference': -20},
298 '101': {'ext': 'webm', 'height': 480, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
299 '102': {'ext': 'webm', 'height': 720, 'format_note': '3D', 'acodec': 'vorbis', 'abr': 192, 'vcodec': 'vp8', 'preference': -20},
301 # Apple HTTP Live Streaming
302 '91': {'ext': 'mp4', 'height': 144, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
303 '92': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
304 '93': {'ext': 'mp4', 'height': 360, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
305 '94': {'ext': 'mp4', 'height': 480, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 128, 'vcodec': 'h264', 'preference': -10},
306 '95': {'ext': 'mp4', 'height': 720, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
307 '96': {'ext': 'mp4', 'height': 1080, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 256, 'vcodec': 'h264', 'preference': -10},
308 '132': {'ext': 'mp4', 'height': 240, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 48, 'vcodec': 'h264', 'preference': -10},
309 '151': {'ext': 'mp4', 'height': 72, 'format_note': 'HLS', 'acodec': 'aac', 'abr': 24, 'vcodec': 'h264', 'preference': -10},
312 '133': {'ext': 'mp4', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
313 '134': {'ext': 'mp4', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
314 '135': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
315 '136': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
316 '137': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
317 '138': {'ext': 'mp4', 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40}, # Height can vary (https://github.com/rg3/youtube-dl/issues/4559)
318 '160': {'ext': 'mp4', 'height': 144, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
319 '212': {'ext': 'mp4', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
320 '264': {'ext': 'mp4', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
321 '298': {'ext': 'mp4', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60, 'preference': -40},
322 '299': {'ext': 'mp4', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'h264', 'fps': 60, 'preference': -40},
323 '266': {'ext': 'mp4', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'h264', 'preference': -40},
326 '139': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 48, 'preference': -50, 'container': 'm4a_dash'},
327 '140': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 128, 'preference': -50, 'container': 'm4a_dash'},
328 '141': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'abr': 256, 'preference': -50, 'container': 'm4a_dash'},
329 '256': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'preference': -50, 'container': 'm4a_dash'},
330 '258': {'ext': 'm4a', 'format_note': 'DASH audio', 'acodec': 'aac', 'preference': -50, 'container': 'm4a_dash'},
333 '167': {'ext': 'webm', 'height': 360, 'width': 640, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
334 '168': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
335 '169': {'ext': 'webm', 'height': 720, 'width': 1280, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
336 '170': {'ext': 'webm', 'height': 1080, 'width': 1920, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
337 '218': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
338 '219': {'ext': 'webm', 'height': 480, 'width': 854, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp8', 'preference': -40},
339 '278': {'ext': 'webm', 'height': 144, 'format_note': 'DASH video', 'container': 'webm', 'vcodec': 'vp9', 'preference': -40},
340 '242': {'ext': 'webm', 'height': 240, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
341 '243': {'ext': 'webm', 'height': 360, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
342 '244': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
343 '245': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
344 '246': {'ext': 'webm', 'height': 480, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
345 '247': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
346 '248': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
347 '271': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
348 # itag 272 videos are either 3840x2160 (e.g. RtoitU2A-3E) or 7680x4320 (sLprVF6d7Ug)
349 '272': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
350 '302': {'ext': 'webm', 'height': 720, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
351 '303': {'ext': 'webm', 'height': 1080, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
352 '308': {'ext': 'webm', 'height': 1440, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
353 '313': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'preference': -40},
354 '315': {'ext': 'webm', 'height': 2160, 'format_note': 'DASH video', 'vcodec': 'vp9', 'fps': 60, 'preference': -40},
357 '171': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 128, 'preference': -50},
358 '172': {'ext': 'webm', 'acodec': 'vorbis', 'format_note': 'DASH audio', 'abr': 256, 'preference': -50},
360 # Dash webm audio with opus inside
361 '249': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 50, 'preference': -50},
362 '250': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 70, 'preference': -50},
363 '251': {'ext': 'webm', 'format_note': 'DASH audio', 'acodec': 'opus', 'abr': 160, 'preference': -50},
366 '_rtmp': {'protocol': 'rtmp'},
368 _SUBTITLE_FORMATS = ('ttml', 'vtt')
373 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&t=1s&end=9',
377 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
378 'uploader': 'Philipp Hagemeister',
379 'uploader_id': 'phihag',
380 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
381 'upload_date': '20121002',
382 'license': 'Standard YouTube License',
383 'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .',
384 'categories': ['Science & Technology'],
385 'tags': ['youtube-dl'],
387 'dislike_count': int,
393 'url': 'https://www.youtube.com/watch?v=UxxajLWwzqY',
394 'note': 'Test generic use_cipher_signature video (#897)',
398 'upload_date': '20120506',
399 'title': 'Icona Pop - I Love It (feat. Charli XCX) [OFFICIAL VIDEO]',
400 'alt_title': 'I Love It (feat. Charli XCX)',
401 'description': 'md5:f3ceb5ef83a08d95b9d146f973157cc8',
402 'tags': ['Icona Pop i love it', 'sweden', 'pop music', 'big beat records', 'big beat', 'charli',
403 'xcx', 'charli xcx', 'girls', 'hbo', 'i love it', "i don't care", 'icona', 'pop',
404 'iconic ep', 'iconic', 'love', 'it'],
405 'uploader': 'Icona Pop',
406 'uploader_id': 'IconaPop',
407 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IconaPop',
408 'license': 'Standard YouTube License',
409 'creator': 'Icona Pop',
413 'url': 'https://www.youtube.com/watch?v=07FYdnEawAQ',
414 'note': 'Test VEVO video with age protection (#956)',
418 'upload_date': '20130703',
419 'title': 'Justin Timberlake - Tunnel Vision (Explicit)',
420 'alt_title': 'Tunnel Vision',
421 'description': 'md5:64249768eec3bc4276236606ea996373',
422 'uploader': 'justintimberlakeVEVO',
423 'uploader_id': 'justintimberlakeVEVO',
424 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/justintimberlakeVEVO',
425 'license': 'Standard YouTube License',
426 'creator': 'Justin Timberlake',
431 'url': '//www.YouTube.com/watch?v=yZIXLfi8CZQ',
432 'note': 'Embed-only video (#1746)',
436 'upload_date': '20120608',
437 'title': 'Principal Sexually Assaults A Teacher - Episode 117 - 8th June 2012',
438 'description': 'md5:09b78bd971f1e3e289601dfba15ca4f7',
439 'uploader': 'SET India',
440 'uploader_id': 'setindia',
441 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/setindia',
442 'license': 'Standard YouTube License',
447 'url': 'https://www.youtube.com/watch?v=BaW_jenozKc&v=UxxajLWwzqY',
448 'note': 'Use the first video ID in the URL',
452 'title': 'youtube-dl test video "\'/\\ä↭𝕐',
453 'uploader': 'Philipp Hagemeister',
454 'uploader_id': 'phihag',
455 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/phihag',
456 'upload_date': '20121002',
457 'license': 'Standard YouTube License',
458 'description': 'test chars: "\'/\\ä↭𝕐\ntest URL: https://github.com/rg3/youtube-dl/issues/1892\n\nThis is a test video for youtube-dl.\n\nFor more information, contact phihag@phihag.de .',
459 'categories': ['Science & Technology'],
460 'tags': ['youtube-dl'],
462 'dislike_count': int,
465 'skip_download': True,
469 'url': 'https://www.youtube.com/watch?v=a9LDPn-MO4I',
470 'note': '256k DASH audio (format 141) via DASH manifest',
474 'upload_date': '20121002',
475 'uploader_id': '8KVIDEO',
476 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/8KVIDEO',
478 'uploader': '8KVIDEO',
479 'license': 'Standard YouTube License',
480 'title': 'UHDTV TEST 8K VIDEO.mp4'
483 'youtube_include_dash_manifest': True,
486 'skip': 'format 141 not served anymore',
488 # DASH manifest with encrypted signature
490 'url': 'https://www.youtube.com/watch?v=IB3lcPjvWLA',
494 'title': 'Afrojack, Spree Wilson - The Spark ft. Spree Wilson',
495 'description': 'md5:12e7067fa6735a77bdcbb58cb1187d2d',
496 'uploader': 'AfrojackVEVO',
497 'uploader_id': 'AfrojackVEVO',
498 'upload_date': '20131011',
499 'license': 'Standard YouTube License',
502 'youtube_include_dash_manifest': True,
503 'format': '141/bestaudio[ext=m4a]',
506 # JS player signature function name containing $
508 'url': 'https://www.youtube.com/watch?v=nfWlot6h_JM',
512 'title': 'Taylor Swift - Shake It Off',
513 'alt_title': 'Shake It Off',
514 'description': 'md5:95f66187cd7c8b2c13eb78e1223b63c3',
515 'uploader': 'TaylorSwiftVEVO',
516 'uploader_id': 'TaylorSwiftVEVO',
517 'upload_date': '20140818',
518 'license': 'Standard YouTube License',
519 'creator': 'Taylor Swift',
522 'youtube_include_dash_manifest': True,
523 'format': '141/bestaudio[ext=m4a]',
528 'url': 'https://www.youtube.com/watch?v=T4XJQO3qol8',
532 'upload_date': '20100909',
533 'uploader': 'The Amazing Atheist',
534 'uploader_id': 'TheAmazingAtheist',
535 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheAmazingAtheist',
536 'license': 'Standard YouTube License',
537 'title': 'Burning Everyone\'s Koran',
538 'description': 'SUBSCRIBE: http://www.youtube.com/saturninefilms\n\nEven Obama has taken a stand against freedom on this issue: http://www.huffingtonpost.com/2010/09/09/obama-gma-interview-quran_n_710282.html',
541 # Normal age-gate video (No vevo, embed allowed)
543 'url': 'https://youtube.com/watch?v=HtVdAasjOgU',
547 'title': 'The Witcher 3: Wild Hunt - The Sword Of Destiny Trailer',
548 'description': r're:(?s).{100,}About the Game\n.*?The Witcher 3: Wild Hunt.{100,}',
549 'uploader': 'The Witcher',
550 'uploader_id': 'WitcherGame',
551 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/WitcherGame',
552 'upload_date': '20140605',
553 'license': 'Standard YouTube License',
557 # Age-gate video with encrypted signature
559 'url': 'https://www.youtube.com/watch?v=6kLq3WMV1nU',
563 'title': 'Dedication To My Ex (Miss That) (Lyric Video)',
564 'description': 'md5:33765bb339e1b47e7e72b5490139bb41',
565 'uploader': 'LloydVEVO',
566 'uploader_id': 'LloydVEVO',
567 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/LloydVEVO',
568 'upload_date': '20110629',
569 'license': 'Standard YouTube License',
573 # video_info is None (https://github.com/rg3/youtube-dl/issues/4421)
575 'url': '__2ABJjxzNo',
579 'upload_date': '20100430',
580 'uploader_id': 'deadmau5',
581 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/deadmau5',
582 'creator': 'deadmau5',
583 'description': 'md5:12c56784b8032162bb936a5f76d55360',
584 'uploader': 'deadmau5',
585 'license': 'Standard YouTube License',
586 'title': 'Deadmau5 - Some Chords (HD)',
587 'alt_title': 'Some Chords',
589 'expected_warnings': [
590 'DASH manifest missing',
593 # Olympics (https://github.com/rg3/youtube-dl/issues/4431)
595 'url': 'lqQg6PlCWgI',
599 'upload_date': '20150827',
600 'uploader_id': 'olympic',
601 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/olympic',
602 'license': 'Standard YouTube License',
603 'description': 'HO09 - Women - GER-AUS - Hockey - 31 July 2012 - London 2012 Olympic Games',
604 'uploader': 'Olympic',
605 'title': 'Hockey - Women - GER-AUS - London 2012 Olympic Games',
608 'skip_download': 'requires avconv',
613 'url': 'https://www.youtube.com/watch?v=_b-2C3KPAM0',
617 'stretched_ratio': 16 / 9.,
618 'upload_date': '20110310',
619 'uploader_id': 'AllenMeow',
620 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/AllenMeow',
621 'description': 'made by Wacom from Korea | 字幕&加油添醋 by TY\'s Allen | 感謝heylisa00cavey1001同學熱情提供梗及翻譯',
623 'license': 'Standard YouTube License',
624 'title': '[A-made] 變態妍字幕版 太妍 我就是這樣的人',
627 # url_encoded_fmt_stream_map is empty string
629 'url': 'qEJwOuvDf7I',
633 'title': 'Обсуждение судебной практики по выборам 14 сентября 2014 года в Санкт-Петербурге',
635 'upload_date': '20150404',
636 'uploader_id': 'spbelect',
637 'uploader': 'Наблюдатели Петербурга',
640 'skip_download': 'requires avconv',
642 'skip': 'This live event has ended.',
644 # Extraction from multiple DASH manifests (https://github.com/rg3/youtube-dl/pull/6097)
646 'url': 'https://www.youtube.com/watch?v=FIl7x6_3R5Y',
650 'title': 'md5:7b81415841e02ecd4313668cde88737a',
651 'description': 'md5:116377fd2963b81ec4ce64b542173306',
652 'upload_date': '20150625',
653 'uploader_id': 'dorappi2000',
654 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/dorappi2000',
655 'uploader': 'dorappi2000',
656 'license': 'Standard YouTube License',
657 'formats': 'mincount:32',
660 # DASH manifest with segment_list
662 'url': 'https://www.youtube.com/embed/CsmdDsKjzN8',
663 'md5': '8ce563a1d667b599d21064e982ab9e31',
667 'upload_date': '20150501', # According to '<meta itemprop="datePublished"', but in other places it's 20150510
668 'uploader': 'Airtek',
669 'description': 'Retransmisión en directo de la XVIII media maratón de Zaragoza.',
670 'uploader_id': 'UCzTzUmjXxxacNnL8I3m4LnQ',
671 'license': 'Standard YouTube License',
672 'title': 'Retransmisión XVIII Media maratón Zaragoza 2015',
675 'youtube_include_dash_manifest': True,
676 'format': '135', # bestvideo
678 'skip': 'This live event has ended.',
681 # Multifeed videos (multiple cameras), URL is for Main Camera
682 'url': 'https://www.youtube.com/watch?v=jqWvoWXjCVs',
685 'title': 'teamPGP: Rocket League Noob Stream',
686 'description': 'md5:dc7872fb300e143831327f1bae3af010',
692 'title': 'teamPGP: Rocket League Noob Stream (Main Camera)',
693 'description': 'md5:dc7872fb300e143831327f1bae3af010',
694 'upload_date': '20150721',
695 'uploader': 'Beer Games Beer',
696 'uploader_id': 'beergamesbeer',
697 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
698 'license': 'Standard YouTube License',
704 'title': 'teamPGP: Rocket League Noob Stream (kreestuh)',
705 'description': 'md5:dc7872fb300e143831327f1bae3af010',
706 'upload_date': '20150721',
707 'uploader': 'Beer Games Beer',
708 'uploader_id': 'beergamesbeer',
709 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
710 'license': 'Standard YouTube License',
716 'title': 'teamPGP: Rocket League Noob Stream (grizzle)',
717 'description': 'md5:dc7872fb300e143831327f1bae3af010',
718 'upload_date': '20150721',
719 'uploader': 'Beer Games Beer',
720 'uploader_id': 'beergamesbeer',
721 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
722 'license': 'Standard YouTube License',
728 'title': 'teamPGP: Rocket League Noob Stream (zim)',
729 'description': 'md5:dc7872fb300e143831327f1bae3af010',
730 'upload_date': '20150721',
731 'uploader': 'Beer Games Beer',
732 'uploader_id': 'beergamesbeer',
733 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/beergamesbeer',
734 'license': 'Standard YouTube License',
738 'skip_download': True,
742 # Multifeed video with comma in title (see https://github.com/rg3/youtube-dl/issues/8536)
743 'url': 'https://www.youtube.com/watch?v=gVfLd0zydlo',
746 'title': 'DevConf.cz 2016 Day 2 Workshops 1 14:00 - 15:30',
749 'skip': 'Not multifeed anymore',
752 'url': 'https://vid.plus/FlRa-iH7PGw',
753 'only_matching': True,
756 'url': 'https://zwearz.com/watch/9lWxNJF-ufM/electra-woman-dyna-girl-official-trailer-grace-helbig.html',
757 'only_matching': True,
760 # Title with JS-like syntax "};" (see https://github.com/rg3/youtube-dl/issues/7468)
761 # Also tests cut-off URL expansion in video description (see
762 # https://github.com/rg3/youtube-dl/issues/1892,
763 # https://github.com/rg3/youtube-dl/issues/8164)
764 'url': 'https://www.youtube.com/watch?v=lsguqyKfVQg',
768 'title': '{dark walk}; Loki/AC/Dishonored; collab w/Elflover21',
769 'alt_title': 'Dark Walk',
770 'description': 'md5:8085699c11dc3f597ce0410b0dcbb34a',
771 'upload_date': '20151119',
772 'uploader_id': 'IronSoulElf',
773 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/IronSoulElf',
774 'uploader': 'IronSoulElf',
775 'license': 'Standard YouTube License',
776 'creator': 'Todd Haberman, Daniel Law Heath & Aaron Kaplan',
779 'skip_download': True,
783 # Tags with '};' (see https://github.com/rg3/youtube-dl/issues/7468)
784 'url': 'https://www.youtube.com/watch?v=Ms7iBXnlUO8',
785 'only_matching': True,
788 # Video with yt:stretch=17:0
789 'url': 'https://www.youtube.com/watch?v=Q39EVAstoRM',
793 'title': 'Clash Of Clans#14 Dicas De Ataque Para CV 4',
794 'description': 'md5:ee18a25c350637c8faff806845bddee9',
795 'upload_date': '20151107',
796 'uploader_id': 'UCCr7TALkRbo3EtFzETQF1LA',
797 'uploader': 'CH GAMER DROID',
800 'skip_download': True,
802 'skip': 'This video does not exist.',
805 # Video licensed under Creative Commons
806 'url': 'https://www.youtube.com/watch?v=M4gD1WSo5mA',
810 'title': 'md5:e41008789470fc2533a3252216f1c1d1',
811 'description': 'md5:a677553cf0840649b731a3024aeff4cc',
812 'upload_date': '20150127',
813 'uploader_id': 'BerkmanCenter',
814 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/BerkmanCenter',
815 'uploader': 'BerkmanCenter',
816 'license': 'Creative Commons Attribution license (reuse allowed)',
819 'skip_download': True,
823 # Channel-like uploader_url
824 'url': 'https://www.youtube.com/watch?v=eQcmzGIKrzg',
828 'title': 'Democratic Socialism and Foreign Policy | Bernie Sanders',
829 'description': 'md5:dda0d780d5a6e120758d1711d062a867',
830 'upload_date': '20151119',
831 'uploader': 'Bernie 2016',
832 'uploader_id': 'UCH1dpzjCEiGAt8CXkryhkZg',
833 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCH1dpzjCEiGAt8CXkryhkZg',
834 'license': 'Creative Commons Attribution license (reuse allowed)',
837 'skip_download': True,
841 'url': 'https://www.youtube.com/watch?feature=player_embedded&amp;v=V36LpHqtcDY',
842 'only_matching': True,
845 # YouTube Red paid video (https://github.com/rg3/youtube-dl/issues/10059)
846 'url': 'https://www.youtube.com/watch?v=i1Ko8UG-Tdo',
847 'only_matching': True,
850 # Rental video preview
851 'url': 'https://www.youtube.com/watch?v=yYr8q0y5Jfg',
855 'title': 'Piku - Trailer',
856 'description': 'md5:c36bd60c3fd6f1954086c083c72092eb',
857 'upload_date': '20150811',
858 'uploader': 'FlixMatrix',
859 'uploader_id': 'FlixMatrixKaravan',
860 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/FlixMatrixKaravan',
861 'license': 'Standard YouTube License',
864 'skip_download': True,
868 # YouTube Red video with episode data
869 'url': 'https://www.youtube.com/watch?v=iqKdEhx-dD4',
873 'title': 'Isolation - Mind Field (Ep 1)',
874 'description': 'md5:3a72f23c086a1496c9e2c54a25fa0822',
875 'upload_date': '20170118',
876 'uploader': 'Vsauce',
877 'uploader_id': 'Vsauce',
878 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/Vsauce',
879 'license': 'Standard YouTube License',
880 'series': 'Mind Field',
885 'skip_download': True,
887 'expected_warnings': [
888 'Skipping DASH manifest',
893 'url': '1t24XAntNCY',
894 'only_matching': True,
898 def __init__(self, *args, **kwargs):
899 super(YoutubeIE, self).__init__(*args, **kwargs)
900 self._player_cache = {}
902 def report_video_info_webpage_download(self, video_id):
903 """Report attempt to download video info webpage."""
904 self.to_screen('%s: Downloading video info webpage' % video_id)
906 def report_information_extraction(self, video_id):
907 """Report attempt to extract video information."""
908 self.to_screen('%s: Extracting video information' % video_id)
910 def report_unavailable_format(self, video_id, format):
911 """Report extracted video URL."""
912 self.to_screen('%s: Format %s not available' % (video_id, format))
914 def report_rtmp_download(self):
915 """Indicate the download will use the RTMP protocol."""
916 self.to_screen('RTMP download detected')
918 def _signature_cache_id(self, example_sig):
919 """ Return a string representation of a signature """
920 return '.'.join(compat_str(len(part)) for part in example_sig.split('.'))
922 def _extract_signature_function(self, video_id, player_url, example_sig):
924 r'.*?-(?P<id>[a-zA-Z0-9_-]+)(?:/watch_as3|/html5player(?:-new)?|/base)?\.(?P<ext>[a-z]+)$',
927 raise ExtractorError('Cannot identify player %r' % player_url)
928 player_type = id_m.group('ext')
929 player_id = id_m.group('id')
931 # Read from filesystem cache
932 func_id = '%s_%s_%s' % (
933 player_type, player_id, self._signature_cache_id(example_sig))
934 assert os.path.basename(func_id) == func_id
936 cache_spec = self._downloader.cache.load('youtube-sigfuncs', func_id)
937 if cache_spec is not None:
938 return lambda s: ''.join(s[i] for i in cache_spec)
941 'Downloading player %s' % player_url
942 if self._downloader.params.get('verbose') else
943 'Downloading %s player %s' % (player_type, player_id)
945 if player_type == 'js':
946 code = self._download_webpage(
947 player_url, video_id,
949 errnote='Download of %s failed' % player_url)
950 res = self._parse_sig_js(code)
951 elif player_type == 'swf':
952 urlh = self._request_webpage(
953 player_url, video_id,
955 errnote='Download of %s failed' % player_url)
957 res = self._parse_sig_swf(code)
959 assert False, 'Invalid player type %r' % player_type
961 test_string = ''.join(map(compat_chr, range(len(example_sig))))
962 cache_res = res(test_string)
963 cache_spec = [ord(c) for c in cache_res]
965 self._downloader.cache.store('youtube-sigfuncs', func_id, cache_spec)
968 def _print_sig_code(self, func, example_sig):
969 def gen_sig_code(idxs):
970 def _genslice(start, end, step):
971 starts = '' if start == 0 else str(start)
972 ends = (':%d' % (end + step)) if end + step >= 0 else ':'
973 steps = '' if step == 1 else (':%d' % step)
974 return 's[%s%s%s]' % (starts, ends, steps)
977 # Quelch pyflakes warnings - start will be set when step is set
978 start = '(Never used)'
979 for i, prev in zip(idxs[1:], idxs[:-1]):
983 yield _genslice(start, prev, step)
986 if i - prev in [-1, 1]:
995 yield _genslice(start, i, step)
997 test_string = ''.join(map(compat_chr, range(len(example_sig))))
998 cache_res = func(test_string)
999 cache_spec = [ord(c) for c in cache_res]
1000 expr_code = ' + '.join(gen_sig_code(cache_spec))
1001 signature_id_tuple = '(%s)' % (
1002 ', '.join(compat_str(len(p)) for p in example_sig.split('.')))
1003 code = ('if tuple(len(p) for p in s.split(\'.\')) == %s:\n'
1004 ' return %s\n') % (signature_id_tuple, expr_code)
1005 self.to_screen('Extracted signature function:\n' + code)
1007 def _parse_sig_js(self, jscode):
1008 funcname = self._search_regex(
1009 r'\.sig\|\|([a-zA-Z0-9$]+)\(', jscode,
1010 'Initial JS player signature function name')
1012 jsi = JSInterpreter(jscode)
1013 initial_function = jsi.extract_function(funcname)
1014 return lambda s: initial_function([s])
1016 def _parse_sig_swf(self, file_contents):
1017 swfi = SWFInterpreter(file_contents)
1018 TARGET_CLASSNAME = 'SignatureDecipher'
1019 searched_class = swfi.extract_class(TARGET_CLASSNAME)
1020 initial_function = swfi.extract_function(searched_class, 'decipher')
1021 return lambda s: initial_function([s])
1023 def _decrypt_signature(self, s, video_id, player_url, age_gate=False):
1024 """Turn the encrypted s field into a working signature"""
1026 if player_url is None:
1027 raise ExtractorError('Cannot decrypt signature without player_url')
1029 if player_url.startswith('//'):
1030 player_url = 'https:' + player_url
1032 player_id = (player_url, self._signature_cache_id(s))
1033 if player_id not in self._player_cache:
1034 func = self._extract_signature_function(
1035 video_id, player_url, s
1037 self._player_cache[player_id] = func
1038 func = self._player_cache[player_id]
1039 if self._downloader.params.get('youtube_print_sig_code'):
1040 self._print_sig_code(func, s)
1042 except Exception as e:
1043 tb = traceback.format_exc()
1044 raise ExtractorError(
1045 'Signature extraction failed: ' + tb, cause=e)
1047 def _get_subtitles(self, video_id, webpage):
1049 subs_doc = self._download_xml(
1050 'https://video.google.com/timedtext?hl=en&type=list&v=%s' % video_id,
1051 video_id, note=False)
1052 except ExtractorError as err:
1053 self._downloader.report_warning('unable to download video subtitles: %s' % error_to_compat_str(err))
1057 for track in subs_doc.findall('track'):
1058 lang = track.attrib['lang_code']
1059 if lang in sub_lang_list:
1062 for ext in self._SUBTITLE_FORMATS:
1063 params = compat_urllib_parse_urlencode({
1067 'name': track.attrib['name'].encode('utf-8'),
1069 sub_formats.append({
1070 'url': 'https://www.youtube.com/api/timedtext?' + params,
1073 sub_lang_list[lang] = sub_formats
1074 if not sub_lang_list:
1075 self._downloader.report_warning('video doesn\'t have subtitles')
1077 return sub_lang_list
1079 def _get_ytplayer_config(self, video_id, webpage):
1081 # User data may contain arbitrary character sequences that may affect
1082 # JSON extraction with regex, e.g. when '};' is contained the second
1083 # regex won't capture the whole JSON. Yet working around by trying more
1084 # concrete regex first keeping in mind proper quoted string handling
1085 # to be implemented in future that will replace this workaround (see
1086 # https://github.com/rg3/youtube-dl/issues/7468,
1087 # https://github.com/rg3/youtube-dl/pull/7599)
1088 r';ytplayer\.config\s*=\s*({.+?});ytplayer',
1089 r';ytplayer\.config\s*=\s*({.+?});',
1091 config = self._search_regex(
1092 patterns, webpage, 'ytplayer.config', default=None)
1094 return self._parse_json(
1095 uppercase_escape(config), video_id, fatal=False)
1097 def _get_automatic_captions(self, video_id, webpage):
1098 """We need the webpage for getting the captions url, pass it as an
1099 argument to speed up the process."""
1100 self.to_screen('%s: Looking for automatic captions' % video_id)
1101 player_config = self._get_ytplayer_config(video_id, webpage)
1102 err_msg = 'Couldn\'t find automatic captions for %s' % video_id
1103 if not player_config:
1104 self._downloader.report_warning(err_msg)
1107 args = player_config['args']
1108 caption_url = args.get('ttsurl')
1110 timestamp = args['timestamp']
1111 # We get the available subtitles
1112 list_params = compat_urllib_parse_urlencode({
1117 list_url = caption_url + '&' + list_params
1118 caption_list = self._download_xml(list_url, video_id)
1119 original_lang_node = caption_list.find('track')
1120 if original_lang_node is None:
1121 self._downloader.report_warning('Video doesn\'t have automatic captions')
1123 original_lang = original_lang_node.attrib['lang_code']
1124 caption_kind = original_lang_node.attrib.get('kind', '')
1127 for lang_node in caption_list.findall('target'):
1128 sub_lang = lang_node.attrib['lang_code']
1130 for ext in self._SUBTITLE_FORMATS:
1131 params = compat_urllib_parse_urlencode({
1132 'lang': original_lang,
1136 'kind': caption_kind,
1138 sub_formats.append({
1139 'url': caption_url + '&' + params,
1142 sub_lang_list[sub_lang] = sub_formats
1143 return sub_lang_list
1145 # Some videos don't provide ttsurl but rather caption_tracks and
1146 # caption_translation_languages (e.g. 20LmZk1hakA)
1147 caption_tracks = args['caption_tracks']
1148 caption_translation_languages = args['caption_translation_languages']
1149 caption_url = compat_parse_qs(caption_tracks.split(',')[0])['u'][0]
1150 parsed_caption_url = compat_urllib_parse_urlparse(caption_url)
1151 caption_qs = compat_parse_qs(parsed_caption_url.query)
1154 for lang in caption_translation_languages.split(','):
1155 lang_qs = compat_parse_qs(compat_urllib_parse_unquote_plus(lang))
1156 sub_lang = lang_qs.get('lc', [None])[0]
1160 for ext in self._SUBTITLE_FORMATS:
1162 'tlang': [sub_lang],
1165 sub_url = compat_urlparse.urlunparse(parsed_caption_url._replace(
1166 query=compat_urllib_parse_urlencode(caption_qs, True)))
1167 sub_formats.append({
1171 sub_lang_list[sub_lang] = sub_formats
1172 return sub_lang_list
1173 # An extractor error can be raise by the download process if there are
1174 # no automatic captions but there are subtitles
1175 except (KeyError, ExtractorError):
1176 self._downloader.report_warning(err_msg)
1179 def _mark_watched(self, video_id, video_info):
1180 playback_url = video_info.get('videostats_playback_base_url', [None])[0]
1181 if not playback_url:
1183 parsed_playback_url = compat_urlparse.urlparse(playback_url)
1184 qs = compat_urlparse.parse_qs(parsed_playback_url.query)
1186 # cpn generation algorithm is reverse engineered from base.js.
1187 # In fact it works even with dummy cpn.
1188 CPN_ALPHABET = 'abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789-_'
1189 cpn = ''.join((CPN_ALPHABET[random.randint(0, 256) & 63] for _ in range(0, 16)))
1195 playback_url = compat_urlparse.urlunparse(
1196 parsed_playback_url._replace(query=compat_urllib_parse_urlencode(qs, True)))
1198 self._download_webpage(
1199 playback_url, video_id, 'Marking watched',
1200 'Unable to mark watched', fatal=False)
1203 def extract_id(cls, url):
1204 mobj = re.match(cls._VALID_URL, url, re.VERBOSE)
1206 raise ExtractorError('Invalid URL: %s' % url)
1207 video_id = mobj.group(2)
1210 def _extract_from_m3u8(self, manifest_url, video_id):
1213 def _get_urls(_manifest):
1214 lines = _manifest.split('\n')
1215 urls = filter(lambda l: l and not l.startswith('#'),
1218 manifest = self._download_webpage(manifest_url, video_id, 'Downloading formats manifest')
1219 formats_urls = _get_urls(manifest)
1220 for format_url in formats_urls:
1221 itag = self._search_regex(r'itag/(\d+?)/', format_url, 'itag')
1222 url_map[itag] = format_url
1225 def _extract_annotations(self, video_id):
1226 url = 'https://www.youtube.com/annotations_invideo?features=1&legacy=1&video_id=%s' % video_id
1227 return self._download_webpage(url, video_id, note='Searching for annotations.', errnote='Unable to download video annotations.')
1229 def _real_extract(self, url):
1230 url, smuggled_data = unsmuggle_url(url, {})
1233 'http' if self._downloader.params.get('prefer_insecure', False)
1238 parsed_url = compat_urllib_parse_urlparse(url)
1239 for component in [parsed_url.fragment, parsed_url.query]:
1240 query = compat_parse_qs(component)
1241 if start_time is None and 't' in query:
1242 start_time = parse_duration(query['t'][0])
1243 if start_time is None and 'start' in query:
1244 start_time = parse_duration(query['start'][0])
1245 if end_time is None and 'end' in query:
1246 end_time = parse_duration(query['end'][0])
1248 # Extract original video URL from URL with redirection, like age verification, using next_url parameter
1249 mobj = re.search(self._NEXT_URL_RE, url)
1251 url = proto + '://www.youtube.com/' + compat_urllib_parse_unquote(mobj.group(1)).lstrip('/')
1252 video_id = self.extract_id(url)
1255 url = proto + '://www.youtube.com/watch?v=%s&gl=US&hl=en&has_verified=1&bpctr=9999999999' % video_id
1256 video_webpage = self._download_webpage(url, video_id)
1258 # Attempt to extract SWF player URL
1259 mobj = re.search(r'swfConfig.*?"(https?:\\/\\/.*?watch.*?-.*?\.swf)"', video_webpage)
1260 if mobj is not None:
1261 player_url = re.sub(r'\\(.)', r'\1', mobj.group(1))
1267 def add_dash_mpd(video_info):
1268 dash_mpd = video_info.get('dashmpd')
1269 if dash_mpd and dash_mpd[0] not in dash_mpds:
1270 dash_mpds.append(dash_mpd[0])
1273 embed_webpage = None
1275 if re.search(r'player-age-gate-content">', video_webpage) is not None:
1277 # We simulate the access to the video from www.youtube.com/v/{video_id}
1278 # this can be viewed without login into Youtube
1279 url = proto + '://www.youtube.com/embed/%s' % video_id
1280 embed_webpage = self._download_webpage(url, video_id, 'Downloading embed webpage')
1281 data = compat_urllib_parse_urlencode({
1282 'video_id': video_id,
1283 'eurl': 'https://youtube.googleapis.com/v/' + video_id,
1284 'sts': self._search_regex(
1285 r'"sts"\s*:\s*(\d+)', embed_webpage, 'sts', default=''),
1287 video_info_url = proto + '://www.youtube.com/get_video_info?' + data
1288 video_info_webpage = self._download_webpage(
1289 video_info_url, video_id,
1290 note='Refetching age-gated info webpage',
1291 errnote='unable to download video info webpage')
1292 video_info = compat_parse_qs(video_info_webpage)
1293 add_dash_mpd(video_info)
1297 # Try looking directly into the video webpage
1298 ytplayer_config = self._get_ytplayer_config(video_id, video_webpage)
1300 args = ytplayer_config['args']
1301 if args.get('url_encoded_fmt_stream_map'):
1302 # Convert to the same format returned by compat_parse_qs
1303 video_info = dict((k, [v]) for k, v in args.items())
1304 add_dash_mpd(video_info)
1305 # Rental video is not rented but preview is available (e.g.
1306 # https://www.youtube.com/watch?v=yYr8q0y5Jfg,
1307 # https://github.com/rg3/youtube-dl/issues/10532)
1308 if not video_info and args.get('ypc_vid'):
1309 return self.url_result(
1310 args['ypc_vid'], YoutubeIE.ie_key(), video_id=args['ypc_vid'])
1311 if args.get('livestream') == '1' or args.get('live_playback') == 1:
1313 if not video_info or self._downloader.params.get('youtube_include_dash_manifest', True):
1314 # We also try looking in get_video_info since it may contain different dashmpd
1315 # URL that points to a DASH manifest with possibly different itag set (some itags
1316 # are missing from DASH manifest pointed by webpage's dashmpd, some - from DASH
1317 # manifest pointed by get_video_info's dashmpd).
1318 # The general idea is to take a union of itags of both DASH manifests (for example
1319 # video with such 'manifest behavior' see https://github.com/rg3/youtube-dl/issues/6093)
1320 self.report_video_info_webpage_download(video_id)
1321 for el_type in ['&el=info', '&el=embedded', '&el=detailpage', '&el=vevo', '']:
1323 '%s://www.youtube.com/get_video_info?&video_id=%s%s&ps=default&eurl=&gl=US&hl=en'
1324 % (proto, video_id, el_type))
1325 video_info_webpage = self._download_webpage(
1327 video_id, note=False,
1328 errnote='unable to download video info webpage')
1329 get_video_info = compat_parse_qs(video_info_webpage)
1330 if get_video_info.get('use_cipher_signature') != ['True']:
1331 add_dash_mpd(get_video_info)
1333 video_info = get_video_info
1334 if 'token' in get_video_info:
1335 # Different get_video_info requests may report different results, e.g.
1336 # some may report video unavailability, but some may serve it without
1337 # any complaint (see https://github.com/rg3/youtube-dl/issues/7362,
1338 # the original webpage as well as el=info and el=embedded get_video_info
1339 # requests report video unavailability due to geo restriction while
1340 # el=detailpage succeeds and returns valid data). This is probably
1341 # due to YouTube measures against IP ranges of hosting providers.
1342 # Working around by preferring the first succeeded video_info containing
1343 # the token if no such video_info yet was found.
1344 if 'token' not in video_info:
1345 video_info = get_video_info
1347 if 'token' not in video_info:
1348 if 'reason' in video_info:
1349 if 'The uploader has not made this video available in your country.' in video_info['reason']:
1350 regions_allowed = self._html_search_meta('regionsAllowed', video_webpage, default=None)
1352 raise ExtractorError('YouTube said: This video is available in %s only' % (
1353 ', '.join(map(ISO3166Utils.short2full, regions_allowed.split(',')))),
1355 raise ExtractorError(
1356 'YouTube said: %s' % video_info['reason'][0],
1357 expected=True, video_id=video_id)
1359 raise ExtractorError(
1360 '"token" parameter not in video info for unknown reason',
1364 if 'title' in video_info:
1365 video_title = video_info['title'][0]
1367 self._downloader.report_warning('Unable to extract video title')
1371 video_description = get_element_by_id("eow-description", video_webpage)
1372 if video_description:
1373 video_description = re.sub(r'''(?x)
1375 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1376 (?:title|href)="([^"]+)"\s+
1377 (?:[a-zA-Z-]+="[^"]*"\s+)*?
1381 ''', r'\1', video_description)
1382 video_description = clean_html(video_description)
1384 fd_mobj = re.search(r'<meta name="description" content="([^"]+)"', video_webpage)
1386 video_description = unescapeHTML(fd_mobj.group(1))
1388 video_description = ''
1390 if 'multifeed_metadata_list' in video_info and not smuggled_data.get('force_singlefeed', False):
1391 if not self._downloader.params.get('noplaylist'):
1394 multifeed_metadata_list = video_info['multifeed_metadata_list'][0]
1395 for feed in multifeed_metadata_list.split(','):
1396 # Unquote should take place before split on comma (,) since textual
1397 # fields may contain comma as well (see
1398 # https://github.com/rg3/youtube-dl/issues/8536)
1399 feed_data = compat_parse_qs(compat_urllib_parse_unquote_plus(feed))
1401 '_type': 'url_transparent',
1402 'ie_key': 'Youtube',
1404 '%s://www.youtube.com/watch?v=%s' % (proto, feed_data['id'][0]),
1405 {'force_singlefeed': True}),
1406 'title': '%s (%s)' % (video_title, feed_data['title'][0]),
1408 feed_ids.append(feed_data['id'][0])
1410 'Downloading multifeed video (%s) - add --no-playlist to just download video %s'
1411 % (', '.join(feed_ids), video_id))
1412 return self.playlist_result(entries, video_id, video_title, video_description)
1413 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
1415 if 'view_count' in video_info:
1416 view_count = int(video_info['view_count'][0])
1420 # Check for "rental" videos
1421 if 'ypc_video_rental_bar_text' in video_info and 'author' not in video_info:
1422 raise ExtractorError('"rental" videos not supported')
1424 # Start extracting information
1425 self.report_information_extraction(video_id)
1428 if 'author' not in video_info:
1429 raise ExtractorError('Unable to extract uploader name')
1430 video_uploader = compat_urllib_parse_unquote_plus(video_info['author'][0])
1433 video_uploader_id = None
1434 video_uploader_url = None
1436 r'<link itemprop="url" href="(?P<uploader_url>https?://www.youtube.com/(?:user|channel)/(?P<uploader_id>[^"]+))">',
1438 if mobj is not None:
1439 video_uploader_id = mobj.group('uploader_id')
1440 video_uploader_url = mobj.group('uploader_url')
1442 self._downloader.report_warning('unable to extract uploader nickname')
1445 # We try first to get a high quality image:
1446 m_thumb = re.search(r'<span itemprop="thumbnail".*?href="(.*?)">',
1447 video_webpage, re.DOTALL)
1448 if m_thumb is not None:
1449 video_thumbnail = m_thumb.group(1)
1450 elif 'thumbnail_url' not in video_info:
1451 self._downloader.report_warning('unable to extract video thumbnail')
1452 video_thumbnail = None
1453 else: # don't panic if we can't find it
1454 video_thumbnail = compat_urllib_parse_unquote_plus(video_info['thumbnail_url'][0])
1457 upload_date = self._html_search_meta(
1458 'datePublished', video_webpage, 'upload date', default=None)
1460 upload_date = self._search_regex(
1461 [r'(?s)id="eow-date.*?>(.*?)</span>',
1462 r'id="watch-uploader-info".*?>.*?(?:Published|Uploaded|Streamed live|Started) on (.+?)</strong>'],
1463 video_webpage, 'upload date', default=None)
1465 upload_date = ' '.join(re.sub(r'[/,-]', r' ', mobj.group(1)).split())
1466 upload_date = unified_strdate(upload_date)
1468 video_license = self._html_search_regex(
1469 r'<h4[^>]+class="title"[^>]*>\s*License\s*</h4>\s*<ul[^>]*>\s*<li>(.+?)</li',
1470 video_webpage, 'license', default=None)
1472 m_music = re.search(
1473 r'<h4[^>]+class="title"[^>]*>\s*Music\s*</h4>\s*<ul[^>]*>\s*<li>(?P<title>.+?) by (?P<creator>.+?)(?:\(.+?\))?</li',
1476 video_alt_title = remove_quotes(unescapeHTML(m_music.group('title')))
1477 video_creator = clean_html(m_music.group('creator'))
1479 video_alt_title = video_creator = None
1481 m_episode = re.search(
1482 r'<div[^>]+id="watch7-headline"[^>]*>\s*<span[^>]*>.*?>(?P<series>[^<]+)</a></b>\s*S(?P<season>\d+)\s*•\s*E(?P<episode>\d+)</span>',
1485 series = m_episode.group('series')
1486 season_number = int(m_episode.group('season'))
1487 episode_number = int(m_episode.group('episode'))
1489 series = season_number = episode_number = None
1491 m_cat_container = self._search_regex(
1492 r'(?s)<h4[^>]*>\s*Category\s*</h4>\s*<ul[^>]*>(.*?)</ul>',
1493 video_webpage, 'categories', default=None)
1495 category = self._html_search_regex(
1496 r'(?s)<a[^<]+>(.*?)</a>', m_cat_container, 'category',
1498 video_categories = None if category is None else [category]
1500 video_categories = None
1503 unescapeHTML(m.group('content'))
1504 for m in re.finditer(self._meta_regex('og:video:tag'), video_webpage)]
1506 def _extract_count(count_name):
1507 return str_to_int(self._search_regex(
1508 r'-%s-button[^>]+><span[^>]+class="yt-uix-button-content"[^>]*>([\d,]+)</span>'
1509 % re.escape(count_name),
1510 video_webpage, count_name, default=None))
1512 like_count = _extract_count('like')
1513 dislike_count = _extract_count('dislike')
1516 video_subtitles = self.extract_subtitles(video_id, video_webpage)
1517 automatic_captions = self.extract_automatic_captions(video_id, video_webpage)
1519 if 'length_seconds' not in video_info:
1520 self._downloader.report_warning('unable to extract video duration')
1521 video_duration = None
1523 video_duration = int(compat_urllib_parse_unquote_plus(video_info['length_seconds'][0]))
1526 video_annotations = None
1527 if self._downloader.params.get('writeannotations', False):
1528 video_annotations = self._extract_annotations(video_id)
1530 def _map_to_format_list(urlmap):
1532 for itag, video_real_url in urlmap.items():
1535 'url': video_real_url,
1536 'player_url': player_url,
1538 if itag in self._formats:
1539 dct.update(self._formats[itag])
1543 if 'conn' in video_info and video_info['conn'][0].startswith('rtmp'):
1544 self.report_rtmp_download()
1546 'format_id': '_rtmp',
1548 'url': video_info['conn'][0],
1549 'player_url': player_url,
1551 elif len(video_info.get('url_encoded_fmt_stream_map', [''])[0]) >= 1 or len(video_info.get('adaptive_fmts', [''])[0]) >= 1:
1552 encoded_url_map = video_info.get('url_encoded_fmt_stream_map', [''])[0] + ',' + video_info.get('adaptive_fmts', [''])[0]
1553 if 'rtmpe%3Dyes' in encoded_url_map:
1554 raise ExtractorError('rtmpe downloads are not supported, see https://github.com/rg3/youtube-dl/issues/343 for more information.', expected=True)
1556 fmt_list = video_info.get('fmt_list', [''])[0]
1558 for fmt in fmt_list.split(','):
1559 spec = fmt.split('/')
1561 width_height = spec[1].split('x')
1562 if len(width_height) == 2:
1563 formats_spec[spec[0]] = {
1564 'resolution': spec[1],
1565 'width': int_or_none(width_height[0]),
1566 'height': int_or_none(width_height[1]),
1569 for url_data_str in encoded_url_map.split(','):
1570 url_data = compat_parse_qs(url_data_str)
1571 if 'itag' not in url_data or 'url' not in url_data:
1573 format_id = url_data['itag'][0]
1574 url = url_data['url'][0]
1576 if 'sig' in url_data:
1577 url += '&signature=' + url_data['sig'][0]
1578 elif 's' in url_data:
1579 encrypted_sig = url_data['s'][0]
1580 ASSETS_RE = r'"assets":.+?"js":\s*("[^"]+")'
1582 jsplayer_url_json = self._search_regex(
1584 embed_webpage if age_gate else video_webpage,
1585 'JS player URL (1)', default=None)
1586 if not jsplayer_url_json and not age_gate:
1587 # We need the embed website after all
1588 if embed_webpage is None:
1589 embed_url = proto + '://www.youtube.com/embed/%s' % video_id
1590 embed_webpage = self._download_webpage(
1591 embed_url, video_id, 'Downloading embed webpage')
1592 jsplayer_url_json = self._search_regex(
1593 ASSETS_RE, embed_webpage, 'JS player URL')
1595 player_url = json.loads(jsplayer_url_json)
1596 if player_url is None:
1597 player_url_json = self._search_regex(
1598 r'ytplayer\.config.*?"url"\s*:\s*("[^"]+")',
1599 video_webpage, 'age gate player URL')
1600 player_url = json.loads(player_url_json)
1602 if self._downloader.params.get('verbose'):
1603 if player_url is None:
1604 player_version = 'unknown'
1605 player_desc = 'unknown'
1607 if player_url.endswith('swf'):
1608 player_version = self._search_regex(
1609 r'-(.+?)(?:/watch_as3)?\.swf$', player_url,
1610 'flash player', fatal=False)
1611 player_desc = 'flash player %s' % player_version
1613 player_version = self._search_regex(
1614 [r'html5player-([^/]+?)(?:/html5player(?:-new)?)?\.js', r'(?:www|player)-([^/]+)/base\.js'],
1616 'html5 player', fatal=False)
1617 player_desc = 'html5 player %s' % player_version
1619 parts_sizes = self._signature_cache_id(encrypted_sig)
1620 self.to_screen('{%s} signature length %s, %s' %
1621 (format_id, parts_sizes, player_desc))
1623 signature = self._decrypt_signature(
1624 encrypted_sig, video_id, player_url, age_gate)
1625 url += '&signature=' + signature
1626 if 'ratebypass' not in url:
1627 url += '&ratebypass=yes'
1630 'format_id': format_id,
1632 'player_url': player_url,
1634 if format_id in self._formats:
1635 dct.update(self._formats[format_id])
1636 if format_id in formats_spec:
1637 dct.update(formats_spec[format_id])
1639 # Some itags are not included in DASH manifest thus corresponding formats will
1640 # lack metadata (see https://github.com/rg3/youtube-dl/pull/5993).
1641 # Trying to extract metadata from url_encoded_fmt_stream_map entry.
1642 mobj = re.search(r'^(?P<width>\d+)[xX](?P<height>\d+)$', url_data.get('size', [''])[0])
1643 width, height = (int(mobj.group('width')), int(mobj.group('height'))) if mobj else (None, None)
1646 'filesize': int_or_none(url_data.get('clen', [None])[0]),
1647 'tbr': float_or_none(url_data.get('bitrate', [None])[0], 1000),
1650 'fps': int_or_none(url_data.get('fps', [None])[0]),
1651 'format_note': url_data.get('quality_label', [None])[0] or url_data.get('quality', [None])[0],
1653 for key, value in more_fields.items():
1656 type_ = url_data.get('type', [None])[0]
1658 type_split = type_.split(';')
1659 kind_ext = type_split[0].split('/')
1660 if len(kind_ext) == 2:
1662 dct['ext'] = mimetype2ext(type_split[0])
1663 if kind in ('audio', 'video'):
1665 for mobj in re.finditer(
1666 r'(?P<key>[a-zA-Z_-]+)=(?P<quote>["\']?)(?P<val>.+?)(?P=quote)(?:;|$)', type_):
1667 if mobj.group('key') == 'codecs':
1668 codecs = mobj.group('val')
1671 codecs = codecs.split(',')
1672 if len(codecs) == 2:
1673 acodec, vcodec = codecs[1], codecs[0]
1675 acodec, vcodec = (codecs[0], 'none') if kind == 'audio' else ('none', codecs[0])
1681 elif video_info.get('hlsvp'):
1682 manifest_url = video_info['hlsvp'][0]
1683 url_map = self._extract_from_m3u8(manifest_url, video_id)
1684 formats = _map_to_format_list(url_map)
1685 # Accept-Encoding header causes failures in live streams on Youtube and Youtube Gaming
1686 for a_format in formats:
1687 a_format.setdefault('http_headers', {})['Youtubedl-no-compression'] = 'True'
1689 unavailable_message = self._html_search_regex(
1690 r'(?s)<h1[^>]+id="unavailable-message"[^>]*>(.+?)</h1>',
1691 video_webpage, 'unavailable message', default=None)
1692 if unavailable_message:
1693 raise ExtractorError(unavailable_message, expected=True)
1694 raise ExtractorError('no conn, hlsvp or url_encoded_fmt_stream_map information found in video info')
1696 # Look for the DASH manifest
1697 if self._downloader.params.get('youtube_include_dash_manifest', True):
1698 dash_mpd_fatal = True
1699 for mpd_url in dash_mpds:
1702 def decrypt_sig(mobj):
1704 dec_s = self._decrypt_signature(s, video_id, player_url, age_gate)
1705 return '/signature/%s' % dec_s
1707 mpd_url = re.sub(r'/s/([a-fA-F0-9\.]+)', decrypt_sig, mpd_url)
1709 for df in self._extract_mpd_formats(
1710 mpd_url, video_id, fatal=dash_mpd_fatal,
1711 formats_dict=self._formats):
1712 # Do not overwrite DASH format found in some previous DASH manifest
1713 if df['format_id'] not in dash_formats:
1714 dash_formats[df['format_id']] = df
1715 # Additional DASH manifests may end up in HTTP Error 403 therefore
1716 # allow them to fail without bug report message if we already have
1717 # some DASH manifest succeeded. This is temporary workaround to reduce
1718 # burst of bug reports until we figure out the reason and whether it
1719 # can be fixed at all.
1720 dash_mpd_fatal = False
1721 except (ExtractorError, KeyError) as e:
1722 self.report_warning(
1723 'Skipping DASH manifest: %r' % e, video_id)
1725 # Remove the formats we found through non-DASH, they
1726 # contain less info and it can be wrong, because we use
1727 # fixed values (for example the resolution). See
1728 # https://github.com/rg3/youtube-dl/issues/5774 for an
1730 formats = [f for f in formats if f['format_id'] not in dash_formats.keys()]
1731 formats.extend(dash_formats.values())
1733 # Check for malformed aspect ratio
1734 stretched_m = re.search(
1735 r'<meta\s+property="og:video:tag".*?content="yt:stretch=(?P<w>[0-9]+):(?P<h>[0-9]+)">',
1738 w = float(stretched_m.group('w'))
1739 h = float(stretched_m.group('h'))
1740 # yt:stretch may hold invalid ratio data (e.g. for Q39EVAstoRM ratio is 17:0).
1741 # We will only process correct ratios.
1745 if f.get('vcodec') != 'none':
1746 f['stretched_ratio'] = ratio
1748 self._sort_formats(formats)
1750 self.mark_watched(video_id, video_info)
1754 'uploader': video_uploader,
1755 'uploader_id': video_uploader_id,
1756 'uploader_url': video_uploader_url,
1757 'upload_date': upload_date,
1758 'license': video_license,
1759 'creator': video_creator,
1760 'title': video_title,
1761 'alt_title': video_alt_title,
1762 'thumbnail': video_thumbnail,
1763 'description': video_description,
1764 'categories': video_categories,
1766 'subtitles': video_subtitles,
1767 'automatic_captions': automatic_captions,
1768 'duration': video_duration,
1769 'age_limit': 18 if age_gate else 0,
1770 'annotations': video_annotations,
1771 'webpage_url': proto + '://www.youtube.com/watch?v=%s' % video_id,
1772 'view_count': view_count,
1773 'like_count': like_count,
1774 'dislike_count': dislike_count,
1775 'average_rating': float_or_none(video_info.get('avg_rating', [None])[0]),
1778 'start_time': start_time,
1779 'end_time': end_time,
1781 'season_number': season_number,
1782 'episode_number': episode_number,
1786 class YoutubeSharedVideoIE(InfoExtractor):
1787 _VALID_URL = r'(?:https?:)?//(?:www\.)?youtube\.com/shared\?.*\bci=(?P<id>[0-9A-Za-z_-]{11})'
1788 IE_NAME = 'youtube:shared'
1791 'url': 'https://www.youtube.com/shared?ci=1nEzmT-M4fU',
1793 'id': 'uPDB5I9wfp8',
1795 'title': 'Pocoyo: 90 minutos de episódios completos Português para crianças - PARTE 3',
1796 'description': 'md5:d9e4d9346a2dfff4c7dc4c8cec0f546d',
1797 'upload_date': '20160219',
1798 'uploader': 'Pocoyo - Português (BR)',
1799 'uploader_id': 'PocoyoBrazil',
1801 'add_ie': ['Youtube'],
1803 # There are already too many Youtube downloads
1804 'skip_download': True,
1808 def _real_extract(self, url):
1809 video_id = self._match_id(url)
1811 webpage = self._download_webpage(url, video_id)
1813 real_video_id = self._html_search_meta(
1814 'videoId', webpage, 'YouTube video id', fatal=True)
1816 return self.url_result(real_video_id, YoutubeIE.ie_key())
1819 class YoutubePlaylistIE(YoutubePlaylistBaseInfoExtractor):
1820 IE_DESC = 'YouTube.com playlists'
1821 _VALID_URL = r"""(?x)(?:
1827 (?:course|view_play_list|my_playlists|artist|playlist|watch|embed/videoseries)
1828 \? (?:.*?[&;])*? (?:p|a|list)=
1831 youtu\.be/[0-9A-Za-z_-]{11}\?.*?\blist=
1834 (?:PL|LL|EC|UU|FL|RD|UL)?[0-9A-Za-z-_]{10,}
1835 # Top tracks, they can also include dots
1840 ((?:PL|LL|EC|UU|FL|RD|UL)[0-9A-Za-z-_]{10,})
1842 _TEMPLATE_URL = 'https://www.youtube.com/playlist?list=%s&disable_polymer=true'
1843 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})&[^"]*?index=(?P<index>\d+)(?:[^>]+>(?P<title>[^<]+))?'
1844 IE_NAME = 'youtube:playlist'
1846 'url': 'https://www.youtube.com/playlist?list=PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
1848 'title': 'ytdl test PL',
1849 'id': 'PLwiyx1dc3P2JR9N8gQaQN_BCvlSlap7re',
1851 'playlist_count': 3,
1853 'url': 'https://www.youtube.com/playlist?list=PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
1855 'id': 'PLtPgu7CB4gbZDA7i_euNxn75ISqxwZPYx',
1856 'title': 'YDL_Empty_List',
1858 'playlist_count': 0,
1860 'note': 'Playlist with deleted videos (#651). As a bonus, the video #51 is also twice in this list.',
1861 'url': 'https://www.youtube.com/playlist?list=PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
1863 'title': '29C3: Not my department',
1864 'id': 'PLwP_SiAcdui0KVebT0mU9Apz359a4ubsC',
1866 'playlist_count': 95,
1868 'note': 'issue #673',
1869 'url': 'PLBB231211A4F62143',
1871 'title': '[OLD]Team Fortress 2 (Class-based LP)',
1872 'id': 'PLBB231211A4F62143',
1874 'playlist_mincount': 26,
1876 'note': 'Large playlist',
1877 'url': 'https://www.youtube.com/playlist?list=UUBABnxM4Ar9ten8Mdjj1j0Q',
1879 'title': 'Uploads from Cauchemar',
1880 'id': 'UUBABnxM4Ar9ten8Mdjj1j0Q',
1882 'playlist_mincount': 799,
1884 'url': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
1886 'title': 'YDL_safe_search',
1887 'id': 'PLtPgu7CB4gbY9oDN3drwC3cMbJggS7dKl',
1889 'playlist_count': 2,
1892 'url': 'https://www.youtube.com/embed/videoseries?list=PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
1893 'playlist_count': 4,
1896 'id': 'PL6IaIsEjSbf96XFRuNccS_RuEXwNdsoEu',
1899 'note': 'Embedded SWF player',
1900 'url': 'https://www.youtube.com/p/YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ?hl=en_US&fs=1&rel=0',
1901 'playlist_count': 4,
1904 'id': 'YN5VISEtHet5D4NEvfTd0zcgFk84NqFZ',
1907 'note': 'Buggy playlist: the webpage has a "Load more" button but it doesn\'t have more videos',
1908 'url': 'https://www.youtube.com/playlist?list=UUXw-G3eDE9trcvY2sBMM_aA',
1910 'title': 'Uploads from Interstellar Movie',
1911 'id': 'UUXw-G3eDE9trcvY2sBMM_aA',
1913 'playlist_mincount': 21,
1915 # Playlist URL that does not actually serve a playlist
1916 'url': 'https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4',
1918 'id': 'FqZTN594JQw',
1920 'title': "Smiley's People 01 detective, Adventure Series, Action",
1921 'uploader': 'STREEM',
1922 'uploader_id': 'UCyPhqAZgwYWZfxElWVbVJng',
1923 'uploader_url': r're:https?://(?:www\.)?youtube\.com/channel/UCyPhqAZgwYWZfxElWVbVJng',
1924 'upload_date': '20150526',
1925 'license': 'Standard YouTube License',
1926 'description': 'md5:507cdcb5a49ac0da37a920ece610be80',
1927 'categories': ['People & Blogs'],
1930 'dislike_count': int,
1933 'skip_download': True,
1935 'add_ie': [YoutubeIE.ie_key()],
1937 'url': 'https://youtu.be/yeWKywCrFtk?list=PL2qgrgXsNUG5ig9cat4ohreBjYLAPC0J5',
1939 'id': 'yeWKywCrFtk',
1941 'title': 'Small Scale Baler and Braiding Rugs',
1942 'uploader': 'Backus-Page House Museum',
1943 'uploader_id': 'backuspagemuseum',
1944 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/backuspagemuseum',
1945 'upload_date': '20161008',
1946 'license': 'Standard YouTube License',
1947 'description': 'md5:800c0c78d5eb128500bffd4f0b4f2e8a',
1948 'categories': ['Nonprofits & Activism'],
1951 'dislike_count': int,
1955 'skip_download': True,
1958 'url': 'https://youtu.be/uWyaPkt-VOI?list=PL9D9FC436B881BA21',
1959 'only_matching': True,
1962 def _real_initialize(self):
1965 def _extract_mix(self, playlist_id):
1966 # The mixes are generated from a single video
1967 # the id of the playlist is just 'RD' + video_id
1969 last_id = playlist_id[-11:]
1970 for n in itertools.count(1):
1971 url = 'https://youtube.com/watch?v=%s&list=%s' % (last_id, playlist_id)
1972 webpage = self._download_webpage(
1973 url, playlist_id, 'Downloading page {0} of Youtube mix'.format(n))
1974 new_ids = orderedSet(re.findall(
1975 r'''(?xs)data-video-username=".*?".*?
1976 href="/watch\?v=([0-9A-Za-z_-]{11})&[^"]*?list=%s''' % re.escape(playlist_id),
1978 # Fetch new pages until all the videos are repeated, it seems that
1979 # there are always 51 unique videos.
1980 new_ids = [_id for _id in new_ids if _id not in ids]
1986 url_results = self._ids_to_results(ids)
1988 search_title = lambda class_name: get_element_by_attribute('class', class_name, webpage)
1990 search_title('playlist-title') or
1991 search_title('title long-title') or
1992 search_title('title'))
1993 title = clean_html(title_span)
1995 return self.playlist_result(url_results, playlist_id, title)
1997 def _extract_playlist(self, playlist_id):
1998 url = self._TEMPLATE_URL % playlist_id
1999 page = self._download_webpage(url, playlist_id)
2001 for match in re.findall(r'<div class="yt-alert-message">([^<]+)</div>', page):
2002 match = match.strip()
2003 # Check if the playlist exists or is private
2004 if re.match(r'[^<]*(The|This) playlist (does not exist|is private)[^<]*', match):
2005 raise ExtractorError(
2006 'The playlist doesn\'t exist or is private, use --username or '
2007 '--netrc to access it.',
2009 elif re.match(r'[^<]*Invalid parameters[^<]*', match):
2010 raise ExtractorError(
2011 'Invalid parameters. Maybe URL is incorrect.',
2013 elif re.match(r'[^<]*Choose your language[^<]*', match):
2016 self.report_warning('Youtube gives an alert message: ' + match)
2018 playlist_title = self._html_search_regex(
2019 r'(?s)<h1 class="pl-header-title[^"]*"[^>]*>\s*(.*?)\s*</h1>',
2020 page, 'title', default=None)
2024 if not playlist_title:
2026 # Some playlist URLs don't actually serve a playlist (e.g.
2027 # https://www.youtube.com/watch?v=FqZTN594JQw&list=PLMYEtVRpaqY00V9W81Cwmzp6N6vZqfUKD4)
2028 next(self._entries(page, playlist_id))
2029 except StopIteration:
2032 return has_videos, self.playlist_result(
2033 self._entries(page, playlist_id), playlist_id, playlist_title)
2035 def _check_download_just_video(self, url, playlist_id):
2036 # Check if it's a video-specific URL
2037 query_dict = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
2038 video_id = query_dict.get('v', [None])[0] or self._search_regex(
2039 r'(?:^|//)youtu\.be/([0-9A-Za-z_-]{11})', url,
2040 'video id', default=None)
2042 if self._downloader.params.get('noplaylist'):
2043 self.to_screen('Downloading just video %s because of --no-playlist' % video_id)
2044 return video_id, self.url_result(video_id, 'Youtube', video_id=video_id)
2046 self.to_screen('Downloading playlist %s - add --no-playlist to just download video %s' % (playlist_id, video_id))
2047 return video_id, None
2050 def _real_extract(self, url):
2051 # Extract playlist id
2052 mobj = re.match(self._VALID_URL, url)
2054 raise ExtractorError('Invalid URL: %s' % url)
2055 playlist_id = mobj.group(1) or mobj.group(2)
2057 video_id, video = self._check_download_just_video(url, playlist_id)
2061 if playlist_id.startswith(('RD', 'UL', 'PU')):
2062 # Mixes require a custom extraction process
2063 return self._extract_mix(playlist_id)
2065 has_videos, playlist = self._extract_playlist(playlist_id)
2066 if has_videos or not video_id:
2069 # Some playlist URLs don't actually serve a playlist (see
2070 # https://github.com/rg3/youtube-dl/issues/10537).
2071 # Fallback to plain video extraction if there is a video id
2072 # along with playlist id.
2073 return self.url_result(video_id, 'Youtube', video_id=video_id)
2076 class YoutubeChannelIE(YoutubePlaylistBaseInfoExtractor):
2077 IE_DESC = 'YouTube.com channels'
2078 _VALID_URL = r'https?://(?:youtu\.be|(?:\w+\.)?youtube(?:-nocookie)?\.com)/channel/(?P<id>[0-9A-Za-z_-]+)'
2079 _TEMPLATE_URL = 'https://www.youtube.com/channel/%s/videos'
2080 _VIDEO_RE = r'(?:title="(?P<title>[^"]+)"[^>]+)?href="/watch\?v=(?P<id>[0-9A-Za-z_-]+)&?'
2081 IE_NAME = 'youtube:channel'
2083 'note': 'paginated channel',
2084 'url': 'https://www.youtube.com/channel/UCKfVa3S1e4PHvxWcwyMMg8w',
2085 'playlist_mincount': 91,
2087 'id': 'UUKfVa3S1e4PHvxWcwyMMg8w',
2088 'title': 'Uploads from lex will',
2091 'note': 'Age restricted channel',
2092 # from https://www.youtube.com/user/DeusExOfficial
2093 'url': 'https://www.youtube.com/channel/UCs0ifCMCm1icqRbqhUINa0w',
2094 'playlist_mincount': 64,
2096 'id': 'UUs0ifCMCm1icqRbqhUINa0w',
2097 'title': 'Uploads from Deus Ex',
2102 def suitable(cls, url):
2103 return (False if YoutubePlaylistsIE.suitable(url) or YoutubeLiveIE.suitable(url)
2104 else super(YoutubeChannelIE, cls).suitable(url))
2106 def _build_template_url(self, url, channel_id):
2107 return self._TEMPLATE_URL % channel_id
2109 def _real_extract(self, url):
2110 channel_id = self._match_id(url)
2112 url = self._build_template_url(url, channel_id)
2114 # Channel by page listing is restricted to 35 pages of 30 items, i.e. 1050 videos total (see #5778)
2115 # Workaround by extracting as a playlist if managed to obtain channel playlist URL
2116 # otherwise fallback on channel by page extraction
2117 channel_page = self._download_webpage(
2118 url + '?view=57', channel_id,
2119 'Downloading channel page', fatal=False)
2120 if channel_page is False:
2121 channel_playlist_id = False
2123 channel_playlist_id = self._html_search_meta(
2124 'channelId', channel_page, 'channel id', default=None)
2125 if not channel_playlist_id:
2126 channel_url = self._html_search_meta(
2127 ('al:ios:url', 'twitter:app:url:iphone', 'twitter:app:url:ipad'),
2128 channel_page, 'channel url', default=None)
2130 channel_playlist_id = self._search_regex(
2131 r'vnd\.youtube://user/([0-9A-Za-z_-]+)',
2132 channel_url, 'channel id', default=None)
2133 if channel_playlist_id and channel_playlist_id.startswith('UC'):
2134 playlist_id = 'UU' + channel_playlist_id[2:]
2135 return self.url_result(
2136 compat_urlparse.urljoin(url, '/playlist?list=%s' % playlist_id), 'YoutubePlaylist')
2138 channel_page = self._download_webpage(url, channel_id, 'Downloading page #1')
2139 autogenerated = re.search(r'''(?x)
2141 channel-header-autogenerated-label|
2142 yt-channel-title-autogenerated
2143 )[^"]*"''', channel_page) is not None
2146 # The videos are contained in a single page
2147 # the ajax pages can't be used, they are empty
2150 video_id, 'Youtube', video_id=video_id,
2151 video_title=video_title)
2152 for video_id, video_title in self.extract_videos_from_page(channel_page)]
2153 return self.playlist_result(entries, channel_id)
2156 next(self._entries(channel_page, channel_id))
2157 except StopIteration:
2158 alert_message = self._html_search_regex(
2159 r'(?s)<div[^>]+class=(["\']).*?\byt-alert-message\b.*?\1[^>]*>(?P<alert>[^<]+)</div>',
2160 channel_page, 'alert', default=None, group='alert')
2162 raise ExtractorError('Youtube said: %s' % alert_message, expected=True)
2164 return self.playlist_result(self._entries(channel_page, channel_id), channel_id)
2167 class YoutubeUserIE(YoutubeChannelIE):
2168 IE_DESC = 'YouTube.com user videos (URL or "ytuser" keyword)'
2169 _VALID_URL = r'(?:(?:https?://(?:\w+\.)?youtube\.com/(?:(?P<user>user|c)/)?(?!(?:attribution_link|watch|results)(?:$|[^a-z_A-Z0-9-])))|ytuser:)(?!feed/)(?P<id>[A-Za-z0-9_-]+)'
2170 _TEMPLATE_URL = 'https://www.youtube.com/%s/%s/videos'
2171 IE_NAME = 'youtube:user'
2174 'url': 'https://www.youtube.com/user/TheLinuxFoundation',
2175 'playlist_mincount': 320,
2177 'id': 'UUfX55Sx5hEFjoC3cNs6mCUQ',
2178 'title': 'Uploads from The Linux Foundation',
2181 # Only available via https://www.youtube.com/c/12minuteathlete/videos
2182 # but not https://www.youtube.com/user/12minuteathlete/videos
2183 'url': 'https://www.youtube.com/c/12minuteathlete/videos',
2184 'playlist_mincount': 249,
2186 'id': 'UUVjM-zV6_opMDx7WYxnjZiQ',
2187 'title': 'Uploads from 12 Minute Athlete',
2190 'url': 'ytuser:phihag',
2191 'only_matching': True,
2193 'url': 'https://www.youtube.com/c/gametrailers',
2194 'only_matching': True,
2196 'url': 'https://www.youtube.com/gametrailers',
2197 'only_matching': True,
2199 # This channel is not available.
2200 'url': 'https://www.youtube.com/user/kananishinoSMEJ/videos',
2201 'only_matching': True,
2205 def suitable(cls, url):
2206 # Don't return True if the url can be extracted with other youtube
2207 # extractor, the regex would is too permissive and it would match.
2208 other_yt_ies = iter(klass for (name, klass) in globals().items() if name.startswith('Youtube') and name.endswith('IE') and klass is not cls)
2209 if any(ie.suitable(url) for ie in other_yt_ies):
2212 return super(YoutubeUserIE, cls).suitable(url)
2214 def _build_template_url(self, url, channel_id):
2215 mobj = re.match(self._VALID_URL, url)
2216 return self._TEMPLATE_URL % (mobj.group('user') or 'user', mobj.group('id'))
2219 class YoutubeLiveIE(YoutubeBaseInfoExtractor):
2220 IE_DESC = 'YouTube.com live streams'
2221 _VALID_URL = r'(?P<base_url>https?://(?:\w+\.)?youtube\.com/(?:(?:user|channel|c)/)?(?P<id>[^/]+))/live'
2222 IE_NAME = 'youtube:live'
2225 'url': 'https://www.youtube.com/user/TheYoungTurks/live',
2227 'id': 'a48o2S1cPoo',
2229 'title': 'The Young Turks - Live Main Show',
2230 'uploader': 'The Young Turks',
2231 'uploader_id': 'TheYoungTurks',
2232 'uploader_url': r're:https?://(?:www\.)?youtube\.com/user/TheYoungTurks',
2233 'upload_date': '20150715',
2234 'license': 'Standard YouTube License',
2235 'description': 'md5:438179573adcdff3c97ebb1ee632b891',
2236 'categories': ['News & Politics'],
2237 'tags': ['Cenk Uygur (TV Program Creator)', 'The Young Turks (Award-Winning Work)', 'Talk Show (TV Genre)'],
2239 'dislike_count': int,
2242 'skip_download': True,
2245 'url': 'https://www.youtube.com/channel/UC1yBKRuGpC1tSM73A0ZjYjQ/live',
2246 'only_matching': True,
2248 'url': 'https://www.youtube.com/c/CommanderVideoHq/live',
2249 'only_matching': True,
2251 'url': 'https://www.youtube.com/TheYoungTurks/live',
2252 'only_matching': True,
2255 def _real_extract(self, url):
2256 mobj = re.match(self._VALID_URL, url)
2257 channel_id = mobj.group('id')
2258 base_url = mobj.group('base_url')
2259 webpage = self._download_webpage(url, channel_id, fatal=False)
2261 page_type = self._og_search_property(
2262 'type', webpage, 'page type', default=None)
2263 video_id = self._html_search_meta(
2264 'videoId', webpage, 'video id', default=None)
2265 if page_type == 'video' and video_id and re.match(r'^[0-9A-Za-z_-]{11}$', video_id):
2266 return self.url_result(video_id, YoutubeIE.ie_key())
2267 return self.url_result(base_url)
2270 class YoutubePlaylistsIE(YoutubePlaylistsBaseInfoExtractor):
2271 IE_DESC = 'YouTube.com user/channel playlists'
2272 _VALID_URL = r'https?://(?:\w+\.)?youtube\.com/(?:user|channel)/(?P<id>[^/]+)/playlists'
2273 IE_NAME = 'youtube:playlists'
2276 'url': 'https://www.youtube.com/user/ThirstForScience/playlists',
2277 'playlist_mincount': 4,
2279 'id': 'ThirstForScience',
2280 'title': 'Thirst for Science',
2283 # with "Load more" button
2284 'url': 'https://www.youtube.com/user/igorkle1/playlists?view=1&sort=dd',
2285 'playlist_mincount': 70,
2288 'title': 'Игорь Клейнер',
2291 'url': 'https://www.youtube.com/channel/UCiU1dHvZObB2iP6xkJ__Icw/playlists',
2292 'playlist_mincount': 17,
2294 'id': 'UCiU1dHvZObB2iP6xkJ__Icw',
2295 'title': 'Chem Player',
2300 class YoutubeSearchIE(SearchInfoExtractor, YoutubePlaylistIE):
2301 IE_DESC = 'YouTube.com searches'
2302 # there doesn't appear to be a real limit, for example if you search for
2303 # 'python' you get more than 8.000.000 results
2304 _MAX_RESULTS = float('inf')
2305 IE_NAME = 'youtube:search'
2306 _SEARCH_KEY = 'ytsearch'
2307 _EXTRA_QUERY_ARGS = {}
2310 def _get_n_results(self, query, n):
2311 """Get a specified number of results for a query"""
2316 for pagenum in itertools.count(1):
2318 'search_query': query.encode('utf-8'),
2322 url_query.update(self._EXTRA_QUERY_ARGS)
2323 result_url = 'https://www.youtube.com/results?' + compat_urllib_parse_urlencode(url_query)
2324 data = self._download_json(
2325 result_url, video_id='query "%s"' % query,
2326 note='Downloading page %s' % pagenum,
2327 errnote='Unable to download API page')
2328 html_content = data[1]['body']['content']
2330 if 'class="search-message' in html_content:
2331 raise ExtractorError(
2332 '[youtube] No video results', expected=True)
2334 new_videos = self._ids_to_results(orderedSet(re.findall(
2335 r'href="/watch\?v=(.{11})', html_content)))
2336 videos += new_videos
2337 if not new_videos or len(videos) > limit:
2342 return self.playlist_result(videos, query)
2345 class YoutubeSearchDateIE(YoutubeSearchIE):
2346 IE_NAME = YoutubeSearchIE.IE_NAME + ':date'
2347 _SEARCH_KEY = 'ytsearchdate'
2348 IE_DESC = 'YouTube.com searches, newest videos first'
2349 _EXTRA_QUERY_ARGS = {'search_sort': 'video_date_uploaded'}
2352 class YoutubeSearchURLIE(YoutubePlaylistBaseInfoExtractor):
2353 IE_DESC = 'YouTube.com search URLs'
2354 IE_NAME = 'youtube:search_url'
2355 _VALID_URL = r'https?://(?:www\.)?youtube\.com/results\?(.*?&)?(?:search_query|q)=(?P<query>[^&]+)(?:[&]|$)'
2356 _VIDEO_RE = r'href="\s*/watch\?v=(?P<id>[0-9A-Za-z_-]{11})(?:[^"]*"[^>]+\btitle="(?P<title>[^"]+))?'
2358 'url': 'https://www.youtube.com/results?baz=bar&search_query=youtube-dl+test+video&filters=video&lclk=video',
2359 'playlist_mincount': 5,
2361 'title': 'youtube-dl test video',
2364 'url': 'https://www.youtube.com/results?q=test&sp=EgQIBBgB',
2365 'only_matching': True,
2368 def _real_extract(self, url):
2369 mobj = re.match(self._VALID_URL, url)
2370 query = compat_urllib_parse_unquote_plus(mobj.group('query'))
2371 webpage = self._download_webpage(url, query)
2372 return self.playlist_result(self._process_page(webpage), playlist_title=query)
2375 class YoutubeShowIE(YoutubePlaylistsBaseInfoExtractor):
2376 IE_DESC = 'YouTube.com (multi-season) shows'
2377 _VALID_URL = r'https?://(?:www\.)?youtube\.com/show/(?P<id>[^?#]*)'
2378 IE_NAME = 'youtube:show'
2380 'url': 'https://www.youtube.com/show/airdisasters',
2381 'playlist_mincount': 5,
2383 'id': 'airdisasters',
2384 'title': 'Air Disasters',
2388 def _real_extract(self, url):
2389 playlist_id = self._match_id(url)
2390 return super(YoutubeShowIE, self)._real_extract(
2391 'https://www.youtube.com/show/%s/playlists' % playlist_id)
2394 class YoutubeFeedsInfoExtractor(YoutubeBaseInfoExtractor):
2396 Base class for feed extractors
2397 Subclasses must define the _FEED_NAME and _PLAYLIST_TITLE properties.
2399 _LOGIN_REQUIRED = True
2403 return 'youtube:%s' % self._FEED_NAME
2405 def _real_initialize(self):
2408 def _real_extract(self, url):
2409 page = self._download_webpage(
2410 'https://www.youtube.com/feed/%s' % self._FEED_NAME, self._PLAYLIST_TITLE)
2412 # The extraction process is the same as for playlists, but the regex
2413 # for the video ids doesn't contain an index
2415 more_widget_html = content_html = page
2416 for page_num in itertools.count(1):
2417 matches = re.findall(r'href="\s*/watch\?v=([0-9A-Za-z_-]{11})', content_html)
2419 # 'recommended' feed has infinite 'load more' and each new portion spins
2420 # the same videos in (sometimes) slightly different order, so we'll check
2421 # for unicity and break when portion has no new videos
2422 new_ids = filter(lambda video_id: video_id not in ids, orderedSet(matches))
2428 mobj = re.search(r'data-uix-load-more-href="/?(?P<more>[^"]+)"', more_widget_html)
2432 more = self._download_json(
2433 'https://youtube.com/%s' % mobj.group('more'), self._PLAYLIST_TITLE,
2434 'Downloading page #%s' % page_num,
2435 transform_source=uppercase_escape)
2436 content_html = more['content_html']
2437 more_widget_html = more['load_more_widget_html']
2439 return self.playlist_result(
2440 self._ids_to_results(ids), playlist_title=self._PLAYLIST_TITLE)
2443 class YoutubeWatchLaterIE(YoutubePlaylistIE):
2444 IE_NAME = 'youtube:watchlater'
2445 IE_DESC = 'Youtube watch later list, ":ytwatchlater" for short (requires authentication)'
2446 _VALID_URL = r'https?://(?:www\.)?youtube\.com/(?:feed/watch_later|(?:playlist|watch)\?(?:.+&)?list=WL)|:ytwatchlater'
2449 'url': 'https://www.youtube.com/playlist?list=WL',
2450 'only_matching': True,
2452 'url': 'https://www.youtube.com/watch?v=bCNU9TrbiRk&index=1&list=WL',
2453 'only_matching': True,
2456 def _real_extract(self, url):
2457 _, video = self._check_download_just_video(url, 'WL')
2460 _, playlist = self._extract_playlist('WL')
2464 class YoutubeFavouritesIE(YoutubeBaseInfoExtractor):
2465 IE_NAME = 'youtube:favorites'
2466 IE_DESC = 'YouTube.com favourite videos, ":ytfav" for short (requires authentication)'
2467 _VALID_URL = r'https?://(?:www\.)?youtube\.com/my_favorites|:ytfav(?:ou?rites)?'
2468 _LOGIN_REQUIRED = True
2470 def _real_extract(self, url):
2471 webpage = self._download_webpage('https://www.youtube.com/my_favorites', 'Youtube Favourites videos')
2472 playlist_id = self._search_regex(r'list=(.+?)["&]', webpage, 'favourites playlist id')
2473 return self.url_result(playlist_id, 'YoutubePlaylist')
2476 class YoutubeRecommendedIE(YoutubeFeedsInfoExtractor):
2477 IE_DESC = 'YouTube.com recommended videos, ":ytrec" for short (requires authentication)'
2478 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/recommended|:ytrec(?:ommended)?'
2479 _FEED_NAME = 'recommended'
2480 _PLAYLIST_TITLE = 'Youtube Recommended videos'
2483 class YoutubeSubscriptionsIE(YoutubeFeedsInfoExtractor):
2484 IE_DESC = 'YouTube.com subscriptions feed, "ytsubs" keyword (requires authentication)'
2485 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/subscriptions|:ytsubs(?:criptions)?'
2486 _FEED_NAME = 'subscriptions'
2487 _PLAYLIST_TITLE = 'Youtube Subscriptions'
2490 class YoutubeHistoryIE(YoutubeFeedsInfoExtractor):
2491 IE_DESC = 'Youtube watch history, ":ythistory" for short (requires authentication)'
2492 _VALID_URL = r'https?://(?:www\.)?youtube\.com/feed/history|:ythistory'
2493 _FEED_NAME = 'history'
2494 _PLAYLIST_TITLE = 'Youtube History'
2497 class YoutubeTruncatedURLIE(InfoExtractor):
2498 IE_NAME = 'youtube:truncated_url'
2499 IE_DESC = False # Do not list
2500 _VALID_URL = r'''(?x)
2502 (?:\w+\.)?[yY][oO][uU][tT][uU][bB][eE](?:-nocookie)?\.com/
2505 annotation_id=annotation_[^&]+|
2511 attribution_link\?a=[^&]+
2517 'url': 'https://www.youtube.com/watch?annotation_id=annotation_3951667041',
2518 'only_matching': True,
2520 'url': 'https://www.youtube.com/watch?',
2521 'only_matching': True,
2523 'url': 'https://www.youtube.com/watch?x-yt-cl=84503534',
2524 'only_matching': True,
2526 'url': 'https://www.youtube.com/watch?feature=foo',
2527 'only_matching': True,
2529 'url': 'https://www.youtube.com/watch?hl=en-GB',
2530 'only_matching': True,
2532 'url': 'https://www.youtube.com/watch?t=2372',
2533 'only_matching': True,
2536 def _real_extract(self, url):
2537 raise ExtractorError(
2538 'Did you forget to quote the URL? Remember that & is a meta '
2539 'character in most shells, so you want to put the URL in quotes, '
2541 '"https://www.youtube.com/watch?feature=foo&v=BaW_jenozKc" '
2542 ' or simply youtube-dl BaW_jenozKc .',
2546 class YoutubeTruncatedIDIE(InfoExtractor):
2547 IE_NAME = 'youtube:truncated_id'
2548 IE_DESC = False # Do not list
2549 _VALID_URL = r'https?://(?:www\.)?youtube\.com/watch\?v=(?P<id>[0-9A-Za-z_-]{1,10})$'
2552 'url': 'https://www.youtube.com/watch?v=N_708QY7Ob',
2553 'only_matching': True,
2556 def _real_extract(self, url):
2557 video_id = self._match_id(url)
2558 raise ExtractorError(
2559 'Incomplete YouTube ID %s. URL %s looks truncated.' % (video_id, url),